IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency

1 code implementation • 24 Aug 2023 • Saeid Ghafouri, Kamran Razavi, Mehran Salmani, Alireza Sanaee, Tania Lorido-Botran, Lin Wang, Joseph Doyle, Pooyan Jamshidi

Model variants are different versions of pre-trained models for the same deep learning task with variations in resource requirements, latency, and accuracy.

Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems

1 code implementation • EuroMLSys 2023 • Mehran Salmani, Saeid Ghafouri, Alireza Sanaee, Kamran Razavi, Max Mühlhäuser, Joseph Doyle, Pooyan Jamshidi, Mohsen Sharifi

Adapting to dynamic workloads considering all the pillars of accuracy, latency, and resource cost is challenging.

Operator as a Service: Stateful Serverless Complex Event Processing

1 code implementation • 9 Dec 2020 • Manisha Luthra, Sebastian Hennig, Kamran Razavi, Lin Wang, Boris Koldehofe

In this paper, we propose CEPLESS, a scalable data management system that decouples the specification from the runtime system by building on the principles of serverless computing.

Networking and Internet Architecture Distributed, Parallel, and Cluster Computing